CN107169458A - Data processing method, device and storage medium - Google Patents
Data processing method, device and storage medium Download PDFInfo
- Publication number
- CN107169458A CN107169458A CN201710351946.6A CN201710351946A CN107169458A CN 107169458 A CN107169458 A CN 107169458A CN 201710351946 A CN201710351946 A CN 201710351946A CN 107169458 A CN107169458 A CN 107169458A
- Authority
- CN
- China
- Prior art keywords
- characteristic parameter
- characteristic
- storage
- facial image
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The embodiments of the invention provide a kind of data processing method, device and storage medium, methods described includes：The identity information and facial image of object to be put in storage are obtained by camera；Feature extraction is carried out to the facial image, characteristic parameter collection is obtained；In-stockroom operation is carried out according to the identity information and the characteristic parameter collection, to realize that the object to be put in storage turns into a member in the registry prestored.It can be realized by the embodiment of the present invention and quick storage processing is carried out to target.
Description
Technical field
The present invention relates to technical field of video monitoring, and in particular to a kind of data processing method, device and storage medium.
Background technology
With economic, society, the fast development of culture, more and more population from other places flow to city so that urban population increases
Plus.The increase of urban population also brings bigger challenge while urbanization process is accelerated to city management, although, video
Monitoring technology provides technical support for urban safety, and at present, including multiple cameras monitoring system in city
Apply to be monitored a region in city, but be due to camera number it is more, and each camera function more
It is independent, it is generally the case that setting up storage then needs keeper to search out target, target is interrogated and examined, to obtain the target
Information is put in storage, storage process is quite cumbersome.Therefore, how to realize that quickly storage (will the mesh to target progress by camera
Mark be entered into monitoring system) mode it is urgently to be resolved hurrily.
The content of the invention
The embodiments of the invention provide a kind of data processing method, device and storage medium, it can be achieved to carry out soon target
Fast storage processing.
First aspect of the embodiment of the present invention provides a kind of data processing method, including：
The identity information and facial image of object to be put in storage are obtained by camera；
Feature extraction is carried out to the facial image, characteristic parameter collection is obtained；
In-stockroom operation is carried out according to the identity information and the characteristic parameter collection, to realize that the object to be put in storage turns into
A member in the registry prestored.
It is described to described with reference to the embodiment of the present invention in a first aspect, in the first possible embodiment of first aspect
Facial image carries out feature extraction, obtains characteristic parameter collection, including：
Feature point extraction is carried out to the facial image, P characteristic point is obtained, the P is the integer more than 1；
The P characteristic point is screened, Q characteristic point is obtained, the Q is the integer less than the P and more than 1；
Using the direction and position of each characteristic point in the Q characteristic point as characteristic parameter, the Q feature is obtained
Parameter；
Contours extract is carried out to the facial image, K feature contour is obtained, and regard the K feature contour as spy
Parameter is levied, the K characteristic parameter is obtained；
The Q characteristic parameter and the K characteristic parameter are synthesized into the characteristic parameter collection.
In this way, above-mentioned the present embodiment, from characteristic point dimension, carries out feature point extraction, also to feature to facial image
The characteristic point that point is obtained after extracting is screened, and can obtain the preferable characteristic point of robustness, and choose the characteristic point after screening
Rower is entered in direction and position compared to feature point number is relied solely in the prior art as characteristic parameter to facial image
Note, which accurately can mark facial image by characteristic point, in addition, carried out from profile angle to facial image again
Contours extract, obtains feature contour, is considered as characteristic parameter, can join the characteristic parameter composite character obtained from two dimensions
Manifold, facial image is marked by characteristic point and profile both direction, and the characteristic parameter collection so obtained more can be anti-
Facial image is mirrored, is conducive to improving the precision of face matching in subsequent applications.
With reference to the first possible embodiment of first aspect of the embodiment of the present invention, second in first aspect may be real
Apply in mode, it is described that the P characteristic point is screened, Q characteristic point is obtained, including：
Determine the central feature point of the P characteristic point；
Chosen from the P characteristic point using the central feature point as the center of circle, and the spy in the range of pre-set radius
Levy a little, obtain the Q characteristic point.
In this way, above-mentioned the present embodiment, can choose a central feature point from characteristic point to be screened, it is special with the center
Levy is a little the center of circle, the characteristic point in the range of pre-set radius, because central feature point is often relatively stable, in addition, the change in image
Change is also gradual change, and thus, the characteristic point around the central feature point is also relatively stable, by this way, can quickly be realized pair
Characteristic point is screened.
With reference to the first or second of possible embodiment of first aspect of the embodiment of the present invention or first aspect, first
In the third possible embodiment of aspect, it is described to the facial image carry out feature extraction, obtain characteristic parameter collection it
Afterwards, and it is described in-stockroom operation is carried out according to the identity information and the characteristic parameter collection before, methods described also includes：
Scanned for, when not searching any matching result, held in the registry according to the characteristic parameter collection
Row is described according to the step of the identity information and characteristic parameter collection progress in-stockroom operation.
In this way, in above-mentioned the present embodiment, due to carrying out in-stockroom operation by camera, can have a kind of situation, that is, image
The facial image that head is photographed may be already present in registry, it is then desired to further scanned in registry, if
Any search result is not obtained, then illustrates above-mentioned facial image not in registry, can carry out in-stockroom operation to it, it is same to avoid
One object repeats to be put in storage.
With reference to the first or second of possible embodiment of first aspect of the embodiment of the present invention or first aspect, first
In 4th kind of possible embodiment of aspect, described according to the identity information and characteristic parameter collection progress in-stockroom operation
Afterwards, methods described also includes：
Obtain the fresh information of the object to be put in storage；
The storage information of the object to be put in storage is updated according to the fresh information.
In this way, above-mentioned the present embodiment, can also continue to be put in storage information to it after the completion of object in-stockroom operation to be put in storage
It is updated and perfect, because storage is a quick implementation process, it is possible to information imperfection when being put in storage, then, can be advanced
Row in-stockroom operation, then when camera captures more information, then the storage information of the object to be put in storage is improved, dynamic can be achieved
Update the storage information in registry.
Second aspect of the embodiment of the present invention provides a kind of data processing equipment, including：
First acquisition unit, identity information and facial image for obtaining object to be put in storage by camera；
Extraction unit, for carrying out feature extraction to the facial image, obtains characteristic parameter collection；
Processing unit, it is described to realize for carrying out in-stockroom operation according to the identity information and the characteristic parameter collection
Object to be put in storage turns into a member in the registry prestored.
It is described to extract single in the first possible embodiment of second aspect with reference to second aspect of the embodiment of the present invention
Member includes：
First extraction module, for carrying out feature point extraction to the facial image, obtains P characteristic point, the P is big
In 1 integer；
Screening module, for being screened to the P characteristic point, obtains Q characteristic point, the Q be less than the P and
Integer more than 1；
First determining module, for the direction and position of each characteristic point in the Q characteristic point to be joined as feature
Number, obtains the Q characteristic parameter；
Second extraction module, for carrying out contours extract to the facial image, obtains K feature contour, and by the K
Individual feature contour obtains the K characteristic parameter as characteristic parameter；
Second determining module, for the Q characteristic parameter and the K characteristic parameter to be synthesized into the characteristic parameter
Collection.
With reference to the first possible embodiment of second aspect of the embodiment of the present invention, second in second aspect may be real
Apply in mode, the screening module specifically for：
Central feature point for determining the P characteristic point, chooses with the central feature from the P characteristic point
Point is the center of circle, and is in the characteristic point in the range of pre-set radius, obtains the Q characteristic point.
With reference to the first or second of possible embodiment of second aspect of the embodiment of the present invention or second aspect, second
In the third possible embodiment of aspect, described device also includes：
Search unit, for carrying out feature extraction to the facial image in the extraction unit, obtains characteristic parameter collection
Afterwards, scanned for according to the characteristic parameter collection in the registry, any matching is not searched in the search unit
When as a result, the step of carrying out in-stockroom operation according to the identity information and the characteristic parameter collection is performed by the processing unit.
With reference to the first or second of possible embodiment of second aspect of the embodiment of the present invention or second aspect, second
In 4th kind of possible embodiment of aspect, described device also includes：
Second acquisition unit, for being entered in the processing unit according to the identity information and the characteristic parameter collection
After the operation of storehouse, the fresh information of the object to be put in storage is obtained；
Updating block, for being updated according to the fresh information to the storage information of the object to be put in storage.
The third aspect of the embodiment of the present invention provides a kind of computer-readable recording medium, and be stored with computer program, institute
Computer program is stated to be executed by processor to realize the side as described in any possible embodiment of first aspect or first aspect
Method.
Implement the embodiment of the present invention, have the advantages that：
As can be seen that by the embodiment of the present invention, data processing equipment can obtain the body of object to be put in storage by camera
Part information and facial image, carry out feature extraction to facial image, obtain characteristic parameter collection, are joined according to identity information and feature
Manifold carries out in-stockroom operation, to realize that object to be put in storage turns into a member in the registry prestored.So as to using shooting
Head obtains the facial image and identity information of object to be put in storage, and further carries out feature extraction to its facial image, is treated
The characteristic parameter collection of object is put in storage, in-stockroom operation is further carried out, due to being cross-examined without treating storage object, but directly
Obtained by camera, warehouse-in efficiency can be improved.For example, in supermarket, suspect object is found in monitor supervision platform, due to not existing
Field can not prevent suspect object, and then, in-stockroom operation can be carried out to the suspect object by the embodiments of the present invention, and notify
Behavior of the staff to suspect object is prevented or handled afterwards.
Brief description of the drawings
Technical scheme in order to illustrate the embodiments of the present invention more clearly, makes required in being described below to embodiment
Accompanying drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the present invention, for ability
For the those of ordinary skill of domain, on the premise of not paying creative work, it can also be obtained according to these accompanying drawings other attached
Figure.
Fig. 1 is a kind of first embodiment schematic flow sheet of data processing method provided in an embodiment of the present invention；
Fig. 2 is a kind of second embodiment schematic flow sheet of data processing method provided in an embodiment of the present invention；
Fig. 3 a are a kind of first embodiment structural representations of data processing equipment provided in an embodiment of the present invention；
Fig. 3 b are the structural representations of the extraction unit of the data processing equipment described by Fig. 3 a provided in an embodiment of the present invention
Figure；
Fig. 3 c are the another structural representations of the data processing equipment described by Fig. 3 a provided in an embodiment of the present invention；
Fig. 3 d are the another structural representations of the data processing equipment described by Fig. 3 a provided in an embodiment of the present invention；
Fig. 4 is a kind of second embodiment structural representation of data processing equipment provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is a part of embodiment of the invention, rather than whole embodiments.Based on this hair
Embodiment in bright, the every other implementation that those of ordinary skill in the art are obtained under the premise of creative work is not made
Example, belongs to the scope of protection of the invention.
Term " first ", " second ", " the 3rd " in description and claims of this specification and the accompanying drawing and "
Four " etc. be to be used to distinguish different objects, rather than for describing particular order.In addition, term " comprising " and " having " and it
Any deformation, it is intended that covering non-exclusive is included.For example contain the process of series of steps or unit, method, be
The step of system, product or equipment are not limited to list or unit, but the step of alternatively also include not listing or list
Member, or alternatively also include for the intrinsic other steps of these processes, method, product or equipment or unit.
Referenced herein " embodiment " is it is meant that the special characteristic, structure or the characteristic that describe can be wrapped in conjunction with the embodiments
In at least one embodiment of the present invention.It is identical that each position in the description shows that the phrase might not be each meant
Embodiment, nor the independent or alternative embodiment with other embodiments mutual exclusion.Those skilled in the art explicitly and
Implicitly understand, embodiment described herein can be combined with other embodiments.
Data processing equipment described by the embodiment of the present invention can include smart mobile phone (such as Android phone, iOS mobile phones,
Windows Phone mobile phones etc.), tablet personal computer, palm PC, notebook computer, mobile internet device (MID, Mobile
Internet Devices) or Wearable etc., above-mentioned is only citing, and non exhaustive, including but not limited to said apparatus, when
So, above-mentioned data processing equipment can also be server.
It should be noted that the data processing equipment in the embodiment of the present invention can be connected with multiple cameras, each shooting
Head is used equally for capturing video image, and each camera can have a corresponding position mark, or, can have one with
Corresponding numbering.Under normal circumstances, camera may be provided at public place, for example, school, museum, crossroad, walking
Street, office building, garage, airport, hospital, subway station, station, bus platform, supermarket, hotel, public place of entertainment etc..Camera exists
Photograph after video image, the memory of system where the video image can be saved in data processing equipment.Can in memory
The multiple images that are stored with storehouse, each image library can include the different video image of same people, and certainly, each image library can also be used
The video image shot in the video image in one region of storage or some specified camera.
Still optionally further, in the embodiment of the present invention, each frame video image that camera is shot corresponds to an attribute
Information, attribute information is following at least one：The shooting time of video image, the position of video image, the attribute of video image
Character features attribute in parameter (form, size, resolution ratio etc.), the numbering and video image of video image.Above-mentioned video figure
Character features attribute as in may include but be not limited only to：Personage's number, character positions, personage's angle in video image etc.
Deng.
Explanation is needed further exist for, the video image of each camera collection is usually dynamic human face image, thus, this
The angle of facial image can be analyzed in inventive embodiments, above-mentioned angle may include but be not limited only to：Horizontally rotate angle
Degree, the angle of pitch or gradient.For example, definable dynamic human face view data two spacing of requirement are not less than 30 pixels, it is proposed that
It is more than 60 pixels.Horizontally rotate angle and be no more than ± 45 ° no more than ± 20 °, inclination angle no more than ± 30 °, the angle of pitch.It is recommended that water
Flat rotational angle is no more than ± 15 ° no more than ± 15 °, the angle of pitch no more than ± 10 °, inclination angle.For example, can also be to facial image
Whether blocked and screened by other objects, it is generally the case that jewelry should not block face's main region, jewelry such as dark colored inks
Mirror, mouth mask and exaggeration jewellery etc., it is of course also possible to be covered with dust all over above camera, cause facial image to be blocked.The present invention
The picture format of video image in embodiment may include but be not limited only to：BMP, JPEG, JPEG2000, PNG etc., its size
Can be between 10-30KB, each video image can also correspond to a shooting time and shoot the shooting of the video image
Head Unified number, (facial image and global picture set up feature pair to the information such as link of the big figure of panorama corresponding with facial image
Answer sexual intercourse file).
Referring to Fig. 1, being a kind of first embodiment schematic flow sheet of data processing method provided in an embodiment of the present invention.
Data processing method described in the present embodiment, comprises the following steps：
101st, the identity information and facial image of object to be put in storage are obtained by camera.
Wherein, the identity information of object to be put in storage may include but be not limited only to：ID card No., height, body weight, family live
Location, cell-phone number, bank's card number, social account, occupation etc..Finding when object is put in storage, this can be obtained by camera and treated
The facial image of object is put in storage, the general image of the object to be put in storage can also be analyzed by camera, to be somebody's turn to do
The height of object to be put in storage, age.Further, the facial image can also be sent to other accessory systems (such as：Public security system
System, banking system, social security sector etc.), identification is carried out to the facial image by other systems, this can be further obtained
The identity information of object to be put in storage, such as：Body weight, home address, cell-phone number, bank's card number, social account, occupation etc..
Alternatively, when performing step 101, it can perform in accordance with the following steps：
11) M the first images of the object to be put in storage, are obtained by camera, the M is the integer more than 1；
12) image quality evaluation, is carried out to the M the first images, the M image quality evaluation values are obtained；
13) image that image quality evaluation values are more than predetermined quality threshold, is chosen from the M image quality evaluation values
Quality evaluation value, obtains N number of image quality evaluation values, and obtains its corresponding first image, obtains the N the first figures
Picture, the N is the integer more than 1 and less than the M；
14), the first image of optimal facial angle is chosen as the facial image from the N the first images；
15), according to being determined the M the first images object to be put in storage identity information.
Wherein, the first image in above-mentioned steps can be the image for treating that storage is related, refer not only to facial image, can be with
It is other images of camera intake, such as：Figure viewed from behind image, side face image etc..Above-mentioned first image may be from one section of video,
Dividing processing can be carried out to one section of video, obtain image one by one, each two field picture is identified, obtain and wait to be put in storage
The related a series of images of object, certainly, not only includes the image of object face to be put in storage, can also wrap in this series of image
Image containing object to be put in storage but not comprising its face, for example, object to be put in storage is leaned to one side, the figure viewed from behind of object to be put in storage.
In realization, first video can be handled using target tracking algorism, obtain treating the related a series of images of storage object, so
Afterwards, each two field picture of the object correlation to be put in storage can be analyzed, such as：Image quality evaluation, choosing are carried out to every two field picture
The preferable image of picture quality is taken, further, the angle of face in each two field picture in the analysis preferable image of picture quality
Degree, because angle is different, the information of its corresponding facial image is also different, it is generally the case that positive angle is optimal, but takes the photograph
If being caught as head, the facial image often closer to positive angle is better, then chooses from these images optimal face angle
The image of degree.For example, object to be put in storage is in motion process, it is more difficult to capture its facial image, thus, multiple its figures can be caught
Picture, chooses the good image of picture quality, then the optimal face of selection angle from picture quality good image from these images
Image, in this way, a suitable facial image can be chosen as the storage image of object to be put in storage, improves and treats storage pair to this
The identification precision of elephant, certainly, if the image that facial image is unintelligible or angle is bad of selection one is schemed as storage
Picture, then, it is follow-up in use, then misrecognition probability is higher.
In above-mentioned steps 15, analyzed using M the first images, obtain the height of the object to be put in storage, build, face
Type etc., as the identity information of the object to be put in storage.For example, the embodiment of the present invention is used for the monitoring system such as market or supermarket
In system, when finding some suspect object, the facial image of the suspect object can be obtained by camera, and pass through camera
Its corresponding identity information is obtained, and then, in-stockroom operation can be carried out to the suspect object in time.Even if in this way, not knowing some
The specific identity information of object, can also carry out storage processing to it, in order to which system records suspect object, be carried out in its next time
In the monitoring range of the monitoring system, staff can be notified to pay close attention in time it.
Wherein, in above-mentioned steps 12, image quality evaluation is carried out to the M the first images, can be in the following way：Can
Image quality evaluation is carried out to image using at least one image quality evaluation index, image quality evaluation values are obtained, wherein, figure
As quality evaluation index may include but be not limited only to：Average gray, mean square deviation, entropy, edge conservation degree, signal to noise ratio etc..It can determine
Justice is bigger for obtained image quality evaluation values, then picture quality is better.
It should be noted that due to when use single evaluation index is evaluated picture quality, with certain limitation
Property, therefore, picture quality can be evaluated using multiple images quality evaluation index, certainly, picture quality is evaluated
When, not image quality evaluation index is The more the better, because image quality evaluation index is more, the meter of image quality assessment process
Calculate complexity higher, it is better also to may not be certain image quality evaluation effect, therefore, higher situation is being required to image quality evaluation
Under, picture quality can be evaluated using 2~10 image quality evaluation indexs.Specifically, image quality evaluation is chosen to refer to
Target number and which index, depending on the situation that implements.Certainly, specifically scene selection picture quality must be also combined to comment
Valency index, carries out carrying out the image quality index of image quality evaluation selection under image quality evaluation and bright ring border under dark situation
Can be different.
Alternatively, in the case of not high to image quality evaluation required precision, an image quality evaluation index can be used
Evaluated, for example, carrying out image quality evaluation values to pending image with entropy, it is believed that entropy is bigger, then illustrates picture quality
It is better, on the contrary, entropy is smaller, then illustrate that picture quality is poorer.
Alternatively, in the case of higher to image quality evaluation required precision, multiple images quality evaluation can be used
Index is treated evaluation image and evaluated, and treating evaluation image in multiple images quality evaluation index carries out image quality evaluation
When, the weight of each image quality evaluation index in the plurality of image quality evaluation index can be set, multiple images matter is can obtain
Evaluation of estimate is measured, final image quality evaluation values, example can obtain according to the plurality of image quality evaluation values and its corresponding weight
Such as, three image quality evaluation indexs are respectively：A indexs, B indexs and C indexs, A weight is a1, and B weight is a2, C's
Weight is a3, when carrying out image quality evaluation to a certain image using A, B and C, and the corresponding image quality evaluation values of A are b1, B couples
The image quality evaluation values answered are b2, and the corresponding image quality evaluation values of C are b3, then, last image quality evaluation values=
a1b1+a2b2+a3b3.Under normal circumstances, image quality evaluation values are bigger, illustrate that picture quality is better.
102nd, feature extraction is carried out to the facial image, obtains characteristic parameter collection.
Wherein, above-mentioned data processing equipment can carry out feature point extraction to facial image or feature contour is extracted, by it
It is used as characteristic parameter collection.The mode of feature extraction may include but be not limited only to：Harris Corner Detection Algorithms, scale invariant feature
(Scale Invariant Feature Transform, SIFT) extraction algorithm, using grader carry out feature extraction, classification
Device may include but be not limited only to：SVMs (Support Vector Machine, SVM), convolutional neural networks, cascade god
Through network, genetic algorithm etc..Certainly, in the case of facial image is unsharp, facial image can also be carried out at enhancing
Reason, enhancing processing may include at least one of following：Smoothing processing, gray scale stretching, histogram equalization, in this way, face can be lifted
The quality of image, on this basis, then carries out feature extraction to enhanced facial image, obtains characteristic parameter collection, now, can
Extract more features.
Alternatively, in above-mentioned steps 102, feature extraction is carried out to the facial image, characteristic parameter collection is obtained, it may include
Following steps：
21) feature point extraction, is carried out to the facial image, P characteristic point is obtained, the P is the integer more than 1；
22), the P characteristic point is screened, Q characteristic point is obtained, the Q is whole less than the P and more than 1
Number；
23), using the direction and position of each characteristic point in the Q characteristic point as characteristic parameter, the Q are obtained
Characteristic parameter；
24) contours extract, is carried out to the facial image, K feature contour is obtained, and the K feature contour is made
Parameter is characterized, the K characteristic parameter is obtained；
25) the P characteristic parameter and the K characteristic parameter, are synthesized into the characteristic parameter collection.
Wherein, data processing equipment first can carry out feature point extraction to facial image, obtain P characteristic point, and P is more than 1
Integer, above-mentioned P characteristic point include carrying out feature point extraction to facial image by the feature point extraction algorithm that pre-sets
Obtained whole characteristic points, the feature point extraction algorithm pre-set may include but be not limited only to：Harris Corner Detection Algorithms,
Scale invariant feature transfer algorithm (Scale-invariant featuretransform, SIFT) algorithm, etc..Due to these
Characteristic point robustness, which differs, to be set, it is then desired to be screened to it, i.e., P characteristic point is screened, is obtained Q feature
Point, Q is the integer less than P and more than 1, mainly filters out the unconspicuous characteristic point of some features, will be each in Q characteristic point
The direction and position of characteristic point are as characteristic parameter, it is intended that enhancing is acted on the mark of facial image, because position
Coordinate position of the characteristic point in facial image is represented, and direction then reflects its direction indication in the position, it is not only rich
The rich characteristic of characteristic point, can also strengthen the Feature point recognition difficulty in face recognition process, can lift the knowledge of facial image
Other precision, therefore, the feature of facial image can be more embodied using the direction and position of characteristic point, so that, it can obtain Q feature
Parameter, secondly, carries out contours extract to facial image, obtains K feature contour, and the K profile is using the wheel pre-set
Wide extraction algorithm carries out whole profiles that contours extract is obtained, and the above-mentioned contours extract algorithm pre-set may include but not only limit
In：Hough transform, Haar operators detection algorithm, Canny operator detection algorithms etc., can regard the K feature contour as feature
Parameter, obtains K characteristic parameter, by Q characteristic parameter and the K characteristic parameter composite character parameter set, in this way, can adopt
Facial image is handled with two dimensions, had using the anti-spurious accuracy of face is improved, because can be profound using two dimensions
The feature to facial image be marked, in face recognition process, not only characteristics of needs Point matching, and characteristics of needs wheel
Exterior feature matching.Alternatively, in above-mentioned steps 22, the P characteristic point is screened, Q characteristic point is obtained, it may include following step
Suddenly：
221) the central feature point of the P characteristic point, is determined；
222), chosen from the P characteristic point using the central feature point as the center of circle, and in the range of pre-set radius
Characteristic point, obtain the Q characteristic point.
Wherein, pre-set radius scope can voluntarily be set or system default by user, and data processing method can be by P feature
Point is mapped in coordinate system, and the central feature point of the P characteristic point is determined using method of geometry, and then, can be from P characteristic point
Choose using the central feature point as the center of circle, the characteristic point in the range of pre-set radius obtains Q characteristic point.Certainly, above-mentioned center is special
Levy one be a little not necessarily in P characteristic point, it is also possible to be the geometric center of P characteristic point, or, in the geometry
Some characteristic point of the heart, so, it may be determined that the characteristic point of characteristic remarkable in facial image, to lift the precision and standard of recognition of face
Exactness.
103rd, in-stockroom operation is carried out according to the identity information and the characteristic parameter collection, to realize the object to be put in storage
As a member in the registry prestored.
Wherein, data processing equipment can preserve the log-on message of identity information and characteristic parameter collection as object to be put in storage
Can also be that object to be put in storage generates a marking code in database, after being put in storage successfully, the object to be put in storage just turns into pre-
A member in the registry first stored.In the manner described above, the in-stockroom operation to different objects can be completed, it is convenient, fast.
As can be seen that by the embodiment of the present invention, data processing equipment can obtain the body of object to be put in storage by camera
Part information and facial image, carry out feature extraction to facial image, obtain characteristic parameter collection, are joined according to identity information and feature
Manifold carries out in-stockroom operation, to realize that object to be put in storage turns into a member in the registry prestored.So as to using shooting
Head obtains the facial image and identity information of object to be put in storage, and further carries out feature extraction to its facial image, is treated
The characteristic parameter collection of object is put in storage, in-stockroom operation is further carried out, due to being cross-examined without treating storage object, but directly
Obtained by camera, warehouse-in efficiency can be improved.For example, in supermarket, suspect object is found in monitor supervision platform, due to not existing
Field can not prevent suspect object, and then, in-stockroom operation can be carried out to the suspect object by the embodiments of the present invention, and notify
Behavior of the staff to suspect object is prevented or handled afterwards.
Consistent with the abovely, referring to Fig. 2, second for a kind of data processing method provided in an embodiment of the present invention implements
Example schematic flow sheet.Data processing method described in the present embodiment, comprises the following steps：
201st, the identity information and facial image of object to be put in storage are obtained by camera.
202nd, feature extraction is carried out to the facial image, obtains characteristic parameter collection.
203rd, scanned for according to the characteristic parameter collection in the registry prestored.
Wherein, data processing equipment, can be according to this feature parameter set after characteristic parameter collection is determined according to facial image
Scanned in registry, it is intended that in order to avoid duplicate registration, in this way, the characteristic parameter collection of matching is being searched,
Then stop registration, when not searching any result, perform step 204.
204th, when not searching any matching result, be put in storage according to the identity information and the characteristic parameter collection
Operation, to realize that the object to be put in storage turns into a member in the registry.
Wherein, any matching result is not being searched, illustrate the data that the object to be put in storage is not present in registry, from
And, in-stockroom operation can be carried out according to the identity information and characteristic parameter collection, to realize that object to be put in storage turns into what is prestored
A member in registry.
205th, the fresh information of the object to be put in storage is obtained.
Wherein, after above-mentioned steps 204, above-mentioned fresh information can be cell-phone number (for example, having changed new cell-phone number), silver
Row card number (for example, having handled new bank's card number), home address (for example, having removed the address of new family) etc..Data processing is filled
Putting can be associated with other systems, and the other systems can be public security system, banking system, social security sector, business system
Etc..In this way, data processing equipment can obtain prefixed time interval or obtained in each other systems information updating treat into
The fresh information of storehouse object.
206th, the storage information of the object to be put in storage is updated according to the fresh information.
Wherein, data processing equipment can receive the fresh information of user's input, and then, update corresponding using fresh information
The storage information of script object to be put in storage, to reach the purpose of renewal.For example, in supermarket, it is suspicious right to be found in monitor supervision platform
As, then can be suspicious right to this by staff after suspect object has been prevented due to suspect object can not do not prevented at the scene
As being cross-examined, the more identity informations of the suspect object are obtained, so that, by the identity information to the storage in script system
Information carries out perfect.
As can be seen that by the embodiment of the present invention, data processing equipment can obtain object to be put in storage identity information and
Facial image, carries out feature extraction to facial image, obtains characteristic parameter collection, searched according to characteristic parameter collection in registry
Rope, when not searching any matching result, carries out in-stockroom operation according to identity information and characteristic parameter collection, waits to be put in storage to realize
Object turns into a member in the registry prestored, after this, can also obtain the fresh information of object to be put in storage, according to
The storage information that fresh information treats storage object is updated.So as to can not only be entered by the characteristic parameter collection of facial image
Row verifies whether object to be put in storage is registered, and then, according to the feature of the identity information of object to be put in storage and facial image
Parameter set carry out in-stockroom operation, can also after the more identity informations of object to be put in storage have been got, treat in time into
The information of storehouse object is updated, and improves warehouse-in efficiency and the efficiency of management.
Consistent with the abovely, device below for the above-mentioned data processing method of implementation, specific as follows：
Fig. 3 a are referred to, are a kind of first embodiment structural representation of data processing equipment provided in an embodiment of the present invention
Figure.Data processing equipment described in the present embodiment, including：First acquisition unit 301, extraction 302 and processing unit 303,
It is specific as follows：
First acquisition unit 301, identity information and facial image for obtaining object to be put in storage by camera；
Extraction unit 302, for carrying out feature extraction to the facial image, obtains characteristic parameter collection；
Processing unit 303, for carrying out in-stockroom operation according to the identity information and the characteristic parameter collection, to realize
Stating object to be put in storage turns into a member in the registry prestored.
Alternatively, first acquisition unit 301 can be included：Image collection module (not marked in figure), image quality evaluation mould
Block (not marked in figure), image choose module (not marked in figure) and identity information determining module (not marked in figure), specifically such as
Under：
Image collection module, M the first images for obtaining the object to be put in storage by camera, the M is big
In 1 integer；
Image quality assessment module, for carrying out image quality evaluation to the M the first images, obtains the M figure
As quality evaluation value；
Image chooses module, for choosing image quality evaluation values from the M image quality evaluation values more than default
The image quality evaluation values of quality threshold, obtain N number of image quality evaluation values, and obtain its corresponding first image, obtain
To the N the first images, the N is the integer more than 1 and less than the M；
Described image chooses module, is additionally operable to choose the first image of optimal facial angle from the N the first images
It is used as the facial image；
Identity information determining module, the identity information for the object to be put in storage according to the M the first images determinations.
Alternatively, the specific refinement knot of the extraction unit 302 of the data processing equipment as described by Fig. 3 b, Fig. 3 b are Fig. 3 a
Structure, the extraction unit includes：First extraction module 3021, screening module 3022, the first determining module 3023, second extract mould
The determining module 3025 of block 3024 and second, it is specific as follows：
First extraction module 3021, for carrying out feature point extraction to the facial image, obtains P characteristic point, the P
For the integer more than 1；
Screening module 3022, for being screened to the P characteristic point, obtains Q characteristic point, the Q is less than institute
State P and the integer more than 1；
First determining module 3023, for regarding the direction and position of each characteristic point in the Q characteristic point as spy
Parameter is levied, the Q characteristic parameter is obtained；
Second extraction module 3024, for carrying out contours extract to the facial image, obtains K feature contour, and will
The K feature contour obtains the K characteristic parameter as characteristic parameter；
Second determining module 3025, for the Q characteristic parameter and the K characteristic parameter to be synthesized into the feature
Parameter set.
Alternatively, the screening module 3022 specifically for：
Central feature point for determining the P characteristic point, chooses with the central feature from the P characteristic point
Point is the center of circle, and is in the characteristic point in the range of pre-set radius, obtains the Q characteristic point.
Alternatively, the another modification structures of the data processing equipment as described by Fig. 3 c, Fig. 3 c are Fig. 3 a, itself and Fig. 3 a phases
Compare, search unit 304 can also be included, it is specific as follows：
Search unit 304, for carrying out feature extraction in 302 pairs of the extraction unit facial image, obtains feature
After parameter set, scanned for according to the characteristic parameter collection in the registry, do not search for and take office in the search unit
During what matching result, performed by the processing unit 303 and storage behaviour is carried out according to the identity information and the characteristic parameter collection
The step of making.
Alternatively, the another modification structures of the data processing equipment as described by Fig. 3 d, Fig. 3 d are Fig. 3 a, itself and Fig. 3 a phases
Compare, second acquisition unit 305 and updating block 306 can also be included, it is specific as follows：
Second acquisition unit 305, in the processing unit 303 according to the identity information and the characteristic parameter collection
Carry out after in-stockroom operation, obtain the fresh information of the object to be put in storage；
Updating block 306, for being updated according to the fresh information to the storage information of the object to be put in storage.
As can be seen that by the embodiment of the present invention, data processing equipment can obtain the body of object to be put in storage by camera
Part information and facial image, carry out feature extraction to facial image, obtain characteristic parameter collection, according to characteristic parameter collection in registration
Scanned in storehouse, when not searching any matching result, in-stockroom operation is carried out according to identity information and characteristic parameter collection, with
Realize that object to be put in storage turns into a member in the registry prestored.So as to obtain object to be put in storage using camera
Facial image and identity information, further carry out feature extraction to its facial image, obtain the characteristic parameter of object to be put in storage
Collection, further carries out in-stockroom operation, due to being cross-examined without treating storage object, but is directly obtained by camera, can
Improve warehouse-in efficiency.For example, in supermarket, finding suspect object in monitor supervision platform, can not preventing suspicious right at the scene due to not
As, and then, in-stockroom operation can be carried out to the suspect object by the embodiments of the present invention, and notify staff to suspicious right
The behavior of elephant is prevented or handled afterwards.
Consistent with the abovely, referring to Fig. 4, second for a kind of data processing equipment provided in an embodiment of the present invention implements
Example structural representation.Data processing equipment described in the present embodiment, including：At least one input equipment 1000；At least one
Individual output equipment 2000；At least one processor 3000, such as CPU；With memory 4000, above-mentioned input equipment 1000, output
Equipment 2000, processor 3000 and memory 4000 are connected by bus 5000.
Wherein, above-mentioned input equipment 1000 concretely contact panel, physical button or mouse.
Above-mentioned output equipment 2000 concretely display screen.
Above-mentioned memory 4000 can be high-speed RAM memory, or nonvolatile storage (non-volatile
Memory), such as magnetic disk storage.Above-mentioned memory 4000 is used to store batch processing code, above-mentioned input equipment 1000, defeated
Going out equipment 2000 and processor 3000 is used to call the program code stored in memory 4000, performs following operation：
Above-mentioned processor 3000, is used for：
The identity information and facial image of object to be put in storage are obtained by camera；
Feature extraction is carried out to the facial image, characteristic parameter collection is obtained；
In-stockroom operation is carried out according to the identity information and the characteristic parameter collection, to realize that the object to be put in storage turns into
A member in the registry prestored.
Alternatively, above-mentioned processor 3000, carries out feature extraction to the facial image, obtains characteristic parameter collection, including：
Feature point extraction is carried out to the facial image, P characteristic point is obtained, the P is the integer more than 1；
The P characteristic point is screened, Q characteristic point is obtained, the Q is the integer less than the P and more than 1；
Using the direction and position of each characteristic point in the Q characteristic point as characteristic parameter, the Q feature is obtained
Parameter；
Contours extract is carried out to the facial image, K feature contour is obtained, and regard the K feature contour as spy
Parameter is levied, the K characteristic parameter is obtained；
The Q characteristic parameter and the K characteristic parameter are synthesized into the characteristic parameter collection.
Alternatively, above-mentioned processor 3000, is screened to the P characteristic point, obtains Q characteristic point, including：
Determine the central feature point of the P characteristic point；
Chosen from the P characteristic point using the central feature point as the center of circle, and the spy in the range of pre-set radius
Levy a little, obtain the Q characteristic point.
Alternatively, above-mentioned processor 3000, carries out feature extraction to the facial image described, obtains characteristic parameter collection
Afterwards, and it is described in-stockroom operation is carried out according to the identity information and the characteristic parameter collection before, also particularly useful for：
Scanned for, when not searching any matching result, held in the registry according to the characteristic parameter collection
Row is described according to the step of the identity information and characteristic parameter collection progress in-stockroom operation.
Alternatively, above-mentioned processor 3000, is put in storage described according to the identity information and the characteristic parameter collection
After operation, also particularly useful for：
Obtain the fresh information of the object to be put in storage；
The storage information of the object to be put in storage is updated according to the fresh information.
The embodiment of the present invention also provides a kind of computer-readable storage medium, wherein, the computer-readable storage medium can be stored with journey
Sequence, the program includes the part or all of step of any data processing method described in the above method embodiment when performing
Suddenly.
Although combining each embodiment herein, invention has been described, however, implementing the present invention for required protection
During, those skilled in the art are by checking the accompanying drawing, disclosure and appended claims, it will be appreciated that and it is real
Other changes of the existing open embodiment.In the claims, the word of " comprising " (comprising) one is not excluded for other compositions
Part or step, "a" or "an" are not excluded for multiple situations.Single processor or other units can realize claim
In some functions enumerating.Mutually different has been recited in mutually different dependent some measures, it is not intended that these are arranged
Apply to combine and produce good effect.
It will be understood by those skilled in the art that embodiments of the invention can be provided as method, device (equipment) or computer journey
Sequence product.Therefore, in terms of the present invention can be using complete hardware embodiment, complete software embodiment or combination software and hardware
The form of embodiment.Moreover, the present invention can be used in one or more calculating for wherein including computer usable program code
The computer program that machine usable storage medium is implemented on (including but is not limited to magnetic disk storage, CD-ROM, optical memory etc.)
The form of product.Computer program is stored/distributed in suitable medium, is provided together with other hardware or as the one of hardware
Part, it would however also be possible to employ other distribution forms, such as passes through the wired or wireless telecommunication systems of Internet or other.
The present invention be with reference to the method for the embodiment of the present invention, device (equipment) and computer program product flow chart with/
Or block diagram is described.It should be understood that can by each flow in computer program instructions implementation process figure and/or block diagram and/
Or square frame and the flow in flow chart and/or block diagram and/or the combination of square frame.These computer program instructions can be provided
To the processor of all-purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices to produce one
Individual machine so that produced by the instruction of computer or the computing device of other programmable data processing devices for realizing
The device for the function of being specified in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames.
These computer program instructions, which may be alternatively stored in, can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory, which is produced, to be included referring to
Make the manufacture of device, the command device realize in one flow of flow chart or multiple flows and/or one square frame of block diagram or
The function of being specified in multiple square frames.
These computer program instructions can be also loaded into computer or other programmable data processing devices so that in meter
Series of operation steps is performed on calculation machine or other programmable devices to produce computer implemented processing, thus in computer or
The instruction performed on other programmable devices is provided for realizing in one flow of flow chart or multiple flows and/or block diagram one
The step of function of being specified in individual square frame or multiple square frames.
Although with reference to specific features and embodiment, invention has been described, it is clear that, do not departing from this hair
In the case of bright spirit and scope, various modifications and combinations can be carried out to it.Correspondingly, the specification and drawings are only institute
The exemplary illustration of the invention that attached claim is defined, and be considered as covered in the scope of the invention any and all and repair
Change, change, combining or equivalent.Obviously, those skilled in the art can to the present invention carry out it is various change and modification without
Depart from the spirit and scope of the present invention.So, if the present invention these modifications and variations belong to the claims in the present invention and its
Within the scope of equivalent technologies, then the present invention is also intended to comprising including these changes and modification.
Claims (10)
1. a kind of data processing method, it is characterised in that including：
The identity information and facial image of object to be put in storage are obtained by camera；
Feature extraction is carried out to the facial image, characteristic parameter collection is obtained；
In-stockroom operation is carried out according to the identity information and the characteristic parameter collection, to realize that the object to be put in storage turns into advance
A member in the registry of storage.
2. according to the method described in claim 1, it is characterised in that described that feature extraction is carried out to the facial image, obtain
Characteristic parameter collection, including：
Feature point extraction is carried out to the facial image, P characteristic point is obtained, the P is the integer more than 1；
The P characteristic point is screened, Q characteristic point is obtained, the Q is the integer less than the P and more than 1；
Using the direction and position of each characteristic point in the Q characteristic point as characteristic parameter, the Q feature ginseng is obtained
Number；
Contours extract is carried out to the facial image, K feature contour is obtained, and the K feature contour is joined as feature
Number, obtains the K characteristic parameter；
The Q characteristic parameter and the K characteristic parameter are synthesized into the characteristic parameter collection.
3. method according to claim 2, it is characterised in that described to be screened to the P characteristic point, obtains Q
Characteristic point, including：
Determine the central feature point of the P characteristic point；
Chosen from the P characteristic point using the central feature point as the center of circle, and the characteristic point in the range of pre-set radius,
Obtain the Q characteristic point.
4. the method according to any one of claims 1 to 3, it is characterised in that spy is carried out to the facial image described
Extraction is levied, after obtaining characteristic parameter collection, and described storage behaviour is carried out according to the identity information and the characteristic parameter collection
Before work, methods described also includes：
Scanned for according to the characteristic parameter collection in the registry, when not searching any matching result, perform institute
State the step of in-stockroom operation is carried out according to the identity information and the characteristic parameter collection.
5. the method according to any one of claims 1 to 3, it is characterised in that described according to the identity information and institute
State after characteristic parameter collection progress in-stockroom operation, methods described also includes：
Obtain the fresh information of the object to be put in storage；
The storage information of the object to be put in storage is updated according to the fresh information.
6. a kind of data processing equipment, it is characterised in that including:
First acquisition unit, identity information and facial image for obtaining object to be put in storage by camera；
Extraction unit, for carrying out feature extraction to the facial image, obtains characteristic parameter collection；
Processing unit, for carrying out in-stockroom operation according to the identity information and the characteristic parameter collection, with realize it is described treat into
Storehouse object turns into a member in the registry prestored.
7. device according to claim 6, it is characterised in that the extraction unit includes：
First extraction module, for carrying out feature point extraction to the facial image, obtains P characteristic point, the P is more than 1
Integer；
Screening module, for being screened to the P characteristic point, obtains Q characteristic point, the Q is less than the P and is more than
1 integer；
First determining module, for the direction and position of each characteristic point in the Q characteristic point, as characteristic parameter, to be obtained
To the Q characteristic parameter；
Second extraction module, for carrying out contours extract to the facial image, obtains K feature contour, and special by described K
Profile is levied as characteristic parameter, the K characteristic parameter is obtained；
Second determining module, for the Q characteristic parameter and the K characteristic parameter to be synthesized into the characteristic parameter collection.
8. device according to claim 7, it is characterised in that the screening module specifically for：
Central feature point for determining the P characteristic point, chosen from the P characteristic point using the central feature point as
The center of circle, and the characteristic point in the range of pre-set radius, obtain the Q characteristic point.
9. the device according to any one of claim 6 to 8, it is characterised in that described device also includes：
Search unit, for carrying out feature extraction to the facial image in the extraction unit, after obtaining characteristic parameter collection,
Scanned for according to the characteristic parameter collection in the registry, any matching result is not searched in the search unit
When, the step of carrying out in-stockroom operation according to the identity information and the characteristic parameter collection is performed by the processing unit.
10. a kind of computer-readable recording medium, be stored with computer program, and the computer program is executed by processor with reality
The existing method as described in claim any one of 1-5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710351946.6A CN107169458B (en) | 2017-05-18 | 2017-05-18 | Data processing method, device and storage medium |
| PCT/CN2018/079370 WO2018210047A1 (en) | 2017-05-18 | 2018-03-16 | Data processing method, data processing apparatus, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710351946.6A CN107169458B (en) | 2017-05-18 | 2017-05-18 | Data processing method, device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107169458A true CN107169458A (en) | 2017-09-15 |
| CN107169458B CN107169458B (en) | 2018-04-06 |
Family
ID=59816193
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710351946.6A Active CN107169458B (en) | 2017-05-18 | 2017-05-18 | Data processing method, device and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN107169458B (en) |
| WO (1) | WO2018210047A1 (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108805800A (en) * | 2018-04-24 | 2018-11-13 | 北京嘀嘀无限科技发展有限公司 | image processing method, device and storage medium |
| WO2018210047A1 (en) * | 2017-05-18 | 2018-11-22 | 深圳云天励飞技术有限公司 | Data processing method, data processing apparatus, electronic device and storage medium |
| CN108921097A (en) * | 2018-07-03 | 2018-11-30 | 深圳市未来感知科技有限公司 | Human eye visual angle detection method, device and computer readable storage medium |
| CN109685040A (en) * | 2019-01-15 | 2019-04-26 | 广州唯品会研究院有限公司 | Measurement method, device and the computer readable storage medium of body data |
| CN109754461A (en) * | 2018-12-29 | 2019-05-14 | 深圳云天励飞技术有限公司 | Image processing method and related product |
| CN109784274A (en) * | 2018-12-29 | 2019-05-21 | 杭州励飞软件技术有限公司 | Identify the method trailed and Related product |
| WO2019223313A1 (en) * | 2018-05-22 | 2019-11-28 | 深圳云天励飞技术有限公司 | Personnel file establishment method and apparatus |
| WO2023040480A1 (en) * | 2021-09-15 | 2023-03-23 | 上海商汤智能科技有限公司 | Image detection method and apparatus, electronic device, and storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109840885B (en) * | 2018-12-27 | 2023-03-14 | 深圳云天励飞技术有限公司 | Image fusion method and related product |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199775A1 (en) * | 2001-05-09 | 2004-10-07 | Wee Ser | Method and device for computer-based processing a template minutia set of a fingerprint and a computer readable storage medium |
| CN101493891A (en) * | 2009-02-27 | 2009-07-29 | 天津大学 | Characteristic extracting and describing method with mirror plate overturning invariability based on SIFT |
| CN101567955A (en) * | 2008-04-23 | 2009-10-28 | 村田机械株式会社 | Image processing apparatus, image scanning apparatus, and image processing method |
| CN101661618A (en) * | 2009-06-05 | 2010-03-03 | 天津大学 | Method for extracting and describing image characteristics with turnover invariance |
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
| CN102236675A (en) * | 2010-04-30 | 2011-11-09 | 华为技术有限公司 | Method for processing matched pairs of characteristic points of images, image retrieval method and image retrieval equipment |
| CN103942705A (en) * | 2014-03-25 | 2014-07-23 | 惠州Tcl移动通信有限公司 | Advertisement classified match pushing method and system based on human face recognition |
| CN104077596A (en) * | 2014-06-18 | 2014-10-01 | 河海大学 | Landmark-free tracking registering method |
| CN104599286A (en) * | 2013-10-31 | 2015-05-06 | 展讯通信(天津)有限公司 | Optical flow based feature tracking method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107169458B (en) * | 2017-05-18 | 2018-04-06 | 深圳云天励飞技术有限公司 | Data processing method, device and storage medium |
-
2017
- 2017-05-18 CN CN201710351946.6A patent/CN107169458B/en active Active
-
2018
- 2018-03-16 WO PCT/CN2018/079370 patent/WO2018210047A1/en active Application Filing
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040199775A1 (en) * | 2001-05-09 | 2004-10-07 | Wee Ser | Method and device for computer-based processing a template minutia set of a fingerprint and a computer readable storage medium |
| CN101567955A (en) * | 2008-04-23 | 2009-10-28 | 村田机械株式会社 | Image processing apparatus, image scanning apparatus, and image processing method |
| CN101493891A (en) * | 2009-02-27 | 2009-07-29 | 天津大学 | Characteristic extracting and describing method with mirror plate overturning invariability based on SIFT |
| CN101661618A (en) * | 2009-06-05 | 2010-03-03 | 天津大学 | Method for extracting and describing image characteristics with turnover invariance |
| CN101770613A (en) * | 2010-01-19 | 2010-07-07 | 北京智慧眼科技发展有限公司 | Social insurance identity authentication method based on face recognition and living body detection |
| CN102236675A (en) * | 2010-04-30 | 2011-11-09 | 华为技术有限公司 | Method for processing matched pairs of characteristic points of images, image retrieval method and image retrieval equipment |
| CN102004908A (en) * | 2010-11-30 | 2011-04-06 | 汉王科技股份有限公司 | Self-adapting face identification method and device |
| CN104599286A (en) * | 2013-10-31 | 2015-05-06 | 展讯通信(天津)有限公司 | Optical flow based feature tracking method and device |
| CN103942705A (en) * | 2014-03-25 | 2014-07-23 | 惠州Tcl移动通信有限公司 | Advertisement classified match pushing method and system based on human face recognition |
| CN104077596A (en) * | 2014-06-18 | 2014-10-01 | 河海大学 | Landmark-free tracking registering method |
Non-Patent Citations (1)
| Title |
|---|
| 杨秋菊: "《基于改进Canny特征点的SIFT算法》", 《计算机工程与设计》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018210047A1 (en) * | 2017-05-18 | 2018-11-22 | 深圳云天励飞技术有限公司 | Data processing method, data processing apparatus, electronic device and storage medium |
| CN108416902A (en) * | 2018-02-28 | 2018-08-17 | 成都果小美网络科技有限公司 | Real-time object identification method based on difference identification and device |
| CN108805800A (en) * | 2018-04-24 | 2018-11-13 | 北京嘀嘀无限科技发展有限公司 | image processing method, device and storage medium |
| WO2019223313A1 (en) * | 2018-05-22 | 2019-11-28 | 深圳云天励飞技术有限公司 | Personnel file establishment method and apparatus |
| CN108921097A (en) * | 2018-07-03 | 2018-11-30 | 深圳市未来感知科技有限公司 | Human eye visual angle detection method, device and computer readable storage medium |
| CN109754461A (en) * | 2018-12-29 | 2019-05-14 | 深圳云天励飞技术有限公司 | Image processing method and related product |
| CN109784274A (en) * | 2018-12-29 | 2019-05-21 | 杭州励飞软件技术有限公司 | Identify the method trailed and Related product |
| CN109784274B (en) * | 2018-12-29 | 2021-09-14 | 杭州励飞软件技术有限公司 | Method for identifying trailing and related product |
| CN109685040A (en) * | 2019-01-15 | 2019-04-26 | 广州唯品会研究院有限公司 | Measurement method, device and the computer readable storage medium of body data |
| WO2023040480A1 (en) * | 2021-09-15 | 2023-03-23 | 上海商汤智能科技有限公司 | Image detection method and apparatus, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2018210047A1 (en) | 2018-11-22 |
| CN107169458B (en) | 2018-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107169458B (en) | Data processing method, device and storage medium | |
| US11830230B2 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN107358146B (en) | Method for processing video frequency, device and storage medium | |
| CN110852160B (en) | Image-based biometric identification system and computer-implemented method | |
| CN109858371B (en) | Face recognition method and device | |
| US8761446B1 (en) | Object detection with false positive filtering | |
| CN106778645B (en) | A kind of image processing method and device | |
| CN106878670B (en) | A kind of method for processing video frequency and device | |
| CN107341443B (en) | Method for processing video frequency, device and storage medium | |
| CN107291810A (en) | Data processing method, device and storage medium | |
| TW202026948A (en) | Methods and devices for biological testing and storage medium thereof | |
| CN106650615B (en) | A kind of image processing method and terminal | |
| CN106791655A (en) | A kind of method for processing video frequency and device | |
| CN111626163B (en) | Human face living body detection method and device and computer equipment | |
| CN109766779A (en) | It hovers personal identification method and Related product | |
| CN112052830B (en) | Method, device and computer storage medium for face detection | |
| CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
| CN109840885B (en) | Image fusion method and related product | |
| CN111767879A (en) | Living body detection method | |
| CN114299569A (en) | Safe face authentication method based on eyeball motion | |
| CN106851199A (en) | A kind of method for processing video frequency and device | |
| CN106937087A (en) | A kind of method for processing video frequency and device | |
| CN107301373B (en) | Data processing method, device and storage medium | |
| Li et al. | Generative adversarial networks-based privacy-preserving 3D reconstruction | |
| CN116881967A (en) | Privacy protection method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |